mlsanityData to 14 Oct 2026

Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks

arXiv 2105.11654 ↗First posted 25 May 2021cs.NE cs.AI cs.CVcited by 78

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from researchers and industry. The most efficient way to train deep SNNs is through ANN-SNN conversion. However, the conversion usually suffers from accuracy loss and long inference time, which impede the practical application of SNN. In this paper, we theoretically analyze ANN-SNN conversion and derive sufficient conditions of the optimal conversion. To better correlate ANN-SNN and get greater accuracy, we propose Rate Norm Layer to replace the ReLU activation function in source ANN training, enabling direct conversion from a trained ANN to an SNN. Moreover, we propose an optimal fit curve to quantify the fit between the activation value of source ANN and the actual firing rate of target SNN. We show that the inference time can be reduced by optimizing the upper bound of the fit curve in the revised ANN to achieve fast inference. Our theory can explain the existing work on fast reasoning and get better results. The experimental results show that the proposed method achieves near loss less conversion with VGG-16, PreActResNet-18, and deeper structures. Moreover, it can reach 8.6x faster reasoning performance under 0.265x energy consumption of the typical method. The code is available at https://github.com/DingJianhao/OptSNNConvertion-RNL-RIL.

Key facts. Cited by 78 papers in the map (data through 14 Oct 2026). Builds on 13 of its 38 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

13 of 38 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  5. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  6. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  7. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  8. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  9. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  10. 2015Spiking Deep Networks with LIF Neuronscited by 63
  11. 2016Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networkscited by 31
  12. 2017BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticitycited by 23
1 more
  1. 2018Spiking Deep Residual Networkcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 14; 2023: 24; 2024: 13; 2025: 18; 2026: 5.

78 papers.

Sort:

By area:

  1. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 169
  2. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  3. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 44
  4. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 41
  5. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  6. 2023Reducing ANN-SNN Conversion Error through Residual Membrane Potentialcited by 40
  7. 2023Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikescited by 40
  8. 2023Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networkscited by 37
  9. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  10. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  11. 2022Exploring Lottery Ticket Hypothesis in Spiking Neural Networkscited by 26
  12. 2021Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networkscited by 23
38 more
  1. 2023ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networkscited by 23
  2. 2023Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Cameracited by 21
  3. 2023Spiking Denoising Diffusion Probabilistic Modelscited by 19
  4. 2023Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networkscited by 18
  5. 2024SpikeZIP-TF: Conversion is All You Need for Transformer-based SNNcited by 18
  6. 2023SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillationcited by 17
  7. 2023Unleashing the Potential of Spiking Neural Networks by Dynamic Confidencecited by 15
  8. 2023Spiking Neural Network for Ultra-low-latency and High-accurate Object Detectioncited by 15
  9. 2025Quantized Spike-driven Transformercited by 13
  10. 2025Towards High-performance Spiking Transformers from ANN to SNN Conversioncited by 11
  11. 2022Meta-learning Spiking Neural Networks with Surrogate Gradient Descentcited by 10
  12. 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 10
  13. 2022A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networkscited by 9
  14. 2023Applications of Spiking Neural Networks in Visual Place Recognitioncited by 9
  15. 2022Spiking SiamFC++: Deep Spiking Neural Network for Object Trackingcited by 8
  16. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  17. 2022Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibrationcited by 7
  18. 2022SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networkscited by 7
  19. 2022Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognitioncited by 7
  20. 2022Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networkscited by 6
  21. 2023AutoST: Training-free Neural Architecture Search for Spiking Transformerscited by 6
  22. 2024Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networkcited by 6
  23. 2025Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networkscited by 6
  24. 2023Automotive Object Detection via Learning Sparse Events by Spiking Neuronscited by 5
  25. 2024FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversioncited by 5
  26. 2025Efficient ANN-SNN Conversion with Error Compensation Learningcited by 4
  27. 2021Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Timecited by 3
  28. 2023MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networkscited by 3
  29. 2023Temporal Contrastive Learning for Spiking Neural Networkscited by 3
  30. 2024Spiking Diffusion Modelscited by 3
  31. 2024Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Camerascited by 3
  32. 2025Spiking Neural Networks Need High Frequency Informationcited by 3
  33. 2025SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaborationcited by 3
  34. 2022SIT: A Bionic and Non-Linear Neuron for Spiking Neural Networkcited by 2
  35. 2022Models Developed for Spiking Neural Networkscited by 2
  36. 2023Highly Efficient SNNs for High-speed Object Detectioncited by 2
  37. 2024One-Spike SNN: Single-Spike Phase Coding with Base Manipulation for ANN-to-SNN Conversion Loss Minimizationcited by 2
  38. 2024Pedestrian intention prediction in Adverse Weather Conditions with Spiking Neural Networks and Dynamic Vision Sensorscited by 2

50 most cited of 78 All 78 (JSON)